Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to updates, changes, or modifications

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "updated."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aden
    -0.90
    vous
    -0.79
    iac
    -0.77
    zees
    -0.77
    avery
    -0.77
    thing
    -0.75
    ¬¼
    -0.73
    ayer
    -0.73
    ppings
    -0.72
    verning
    -0.72
    POSITIVE LOGITS
     updates
    0.82
     notifications
    0.81
     versions
    0.76
     visuals
    0.75
     snapshots
    0.74
     update
    0.73
     accordingly
    0.72
     outdated
    0.71
     updating
    0.70
     formulations
    0.70
    Act Density 0.029%

    No Known Activations